Epipolar-Guided Deep Object Matching for Scene Change Detection
This addresses the problem of viewpoint-robust change detection for mobile cameras like drive recorders, which is incremental as it builds on existing object-based methods by incorporating epipolar constraints.
The paper tackles scene change detection from image pairs captured from different viewpoints by introducing a deep graph matching network that establishes object correspondence, enabling object-wise change detection without precise alignment. Experimental results on synthetic and real datasets verified the network's effectiveness.
This paper describes a viewpoint-robust object-based change detection network (OBJ-CDNet). Mobile cameras such as drive recorders capture images from different viewpoints each time due to differences in camera trajectory and shutter timing. However, previous methods for pixel-wise change detection are vulnerable to the viewpoint differences because they assume aligned image pairs as inputs. To cope with the difficulty, we introduce a deep graph matching network that establishes object correspondence between an image pair. The introduction enables us to detect object-wise scene changes without precise image alignment. For more accurate object matching, we propose an epipolar-guided deep graph matching network (EGMNet), which incorporates the epipolar constraint into the deep graph matching layer used in OBJCDNet. To evaluate our network's robustness against viewpoint differences, we created synthetic and real datasets for scene change detection from an image pair. The experimental results verified the effectiveness of our network.